A Template Based Approach for Training NMT for Low-Resource Uralic Languages - A Pilot with Finnish
Mika K Hämäläinen, Khalid Alnajjar · 2019
In this paper, we present a novel way of building parallel data by filling abstract morphosyntactic structures for endangered low-resource languages that exhibit a rich productive morphology. We use Finnish to pilot our approach by limiting the resources we feed into the machine translation model to the level of the resources available for Erzya. We also present a way of automatically mapping abstract morphosyntactic structures of two languages to produce a parallelized set of templates